C#中如何过滤掉多余的html代码

时间：2011-05-24 来源：笨笨的菜鸟

很方便的，呵呵。过滤掉所有的html标签，

 1  /// <summary>
 2         /// 过滤html标签
 3         /// </summary>
 4         /// <param name="strHtml">html的内容</param>
 5         /// <returns></returns>
 6          public static string StripHTML(string stringToStrip)
 7         {
 8             // paring using RegEx           //
 9             stringToStrip = Regex.Replace(stringToStrip, "</p(?:\\s*)>(?:\\s*)<p(?:\\s*)>", "\n\n", RegexOptions.IgnoreCase | RegexOptions.Compiled);
10             stringToStrip = Regex.Replace(stringToStrip, "<br(?:\\s*)/>", "\n", RegexOptions.IgnoreCase | RegexOptions.Compiled);
11             stringToStrip = Regex.Replace(stringToStrip, "\"", "''", RegexOptions.IgnoreCase | RegexOptions.Compiled);
12             stringToStrip = StripHtmlXmlTags(stringToStrip);
13             return stringToStrip;
14         }
15 
16         private static string StripHtmlXmlTags(string content)
17         {
18             return Regex.Replace(content, "<[^>]+>", "", RegexOptions.IgnoreCase | RegexOptions.Compiled);
19         }